Medical imaging dataset · CT
Multiphase CT abdomen & pelvis, qualified study by study.
The largest collection in our catalogue: contrast-enhanced abdominal CT from a network of Indian hospitals and diagnostic centres, most of it triple-phase, almost all of it paired with a signed radiologist report. Profiled on more than thirty attributes and ready to be qualified against your acceptance criteria.
- 4,300+
- Studies
- 5.8M+
- DICOM images
- 93%
- With radiologist report
- 56%
- Triple-phase
- 81%
- Lossless compression
- 99%
- Thinnest series ≤ 2.5 mm
Rounded inventory figures as of October 2026. Counts move as studies are indexed and qualified; exact eligible counts are returned against your specification.
Composition
Who is in the data
Demographics are carried as bands and recorded on every study profile, so a specification can include, exclude or balance by age and sex before anything is packaged.
Patient sex
- Male60%
- Female40%
Age band
- 0–178%
- 18–3936%
- 40–5934%
- 60–7920%
- 80+2%
At a glance
- Series
- 24,000+
- Mean images per study
- ~1,350
- Acquisition years
- 2022 – 2026
- Source institutions
- 13
Percentages are of studies with the attribute recorded. Figures as of October 2026.
Acquisition profile
How the studies were acquired
Every attribute below is read from the DICOM headers and pixel data of each study, not from a catalogue description. These are the fields your specification can test against.
Contrast & phases
86% contrast-enhanced
Triple-phase 56%, single contrast phase 24%, non-contrast 14%, other multiphase 5%. More than 1,300 studies carry arterial, portal-venous, venous and delayed series together.
Slice thickness
≤ 1.5 mm in 55%
Thinnest reconstructed series is 2.5 mm or finer in 99% of studies. Thick-slice survey series are retained alongside.
Tube voltage
130 kVp in 97%
Remainder at 110 and 120 kVp. kVp is populated in the header for every qualified study.
Bit depth
16-bit stored in 49%
12 bits stored inside a 16-bit allocation in a further 47%, which is the standard export of most CT fleets.
Scanner fleet
Siemens 99%
SOMATOM go.Now two thirds, SOMATOM Scope one third, with a small number of United Imaging and GE systems.
Coverage
~47 cm mean z-extent
Abdomen-with-pelvis coverage in the large majority; abdomen-only studies are flagged separately so you can include or exclude them.
Qualification & delivery
Qualified against your specification, not sold by the terabyte
You do not buy the whole collection. You send inclusion criteria, we return the exact count of studies that pass, and only those are de-identified and delivered.
Specification
We turn your inclusion criteria into a machine-checkable requirement set: modality, anatomy, contrast phase, slice thickness, kVp, bit depth, compression, report pairing and demographic constraints.
Index & profile
Every study is read at header and pixel level and profiled on more than thirty attributes, including phase pattern, scanner model, coverage, compression history and report match.
Verdict per study
Each study receives an eligible, review or reject verdict with the exact criterion codes it failed. Studies whose phase cannot be read from metadata go to a radiologist, not a guess.
De-identify & deliver
Eligible studies are de-identified, re-verified, packaged with a hashed manifest and shipped to your bucket in batches. You load your own pass/fail list and we reconcile against it.
Status of this dataset
This dataset is already in production delivery. More than 2,000 studies have shipped to a US diagnostic AI developer against a written portal-venous specification, and 850+ further studies currently pass that specification in full: lossless, portal-venous series at 2.5 mm or finer, above 100 kVp, 16-bit allocation and exactly one matched report.
Read how the qualification service worksUse cases
What teams build with ct abdomen & pelvis data
Organ and lesion segmentation
Liver, kidney, pancreas and spleen segmentation on portal-venous series, with arterial and delayed phases available for multiphase models.
Phase classification and quality control
Thousands of studies with labelled phase patterns for training models that recognise contrast phase, detect missing phases or flag protocol deviations.
Report-to-image learning
Paired radiologist reports on 93% of studies for vision-language pretraining within the permitted diagnostic scope, report generation and finding localisation.
Incidental finding detection
A broad adult population scanned for mixed indications, suited to models that screen for incidental renal, hepatic and vascular findings.
Pixel-level labels, study-level classification and structured report extraction are available as a clinician-led annotation project. See medical data annotation.
Consent & permitted use
What this data may be used for, stated up front
Every study in the catalogue was obtained under a signed institutional research agreement with the source imaging network, with a data processing agreement on file. The permitted-use scope travels with the data and is written into every delivery manifest.
Permitted purpose
Development, validation and testing of diagnostic AI. Each delivery is matched to a declared purpose before a single study is packaged.
Permitted jurisdictions
United States and India. Deliveries to other jurisdictions require a fresh agreement with the source, which we will tell you plainly if it is not available.
Not permitted
General-purpose or foundation-model pretraining, and onward resale or sublicensing to third parties. We do not sell around the scope of the source agreement.
Retention
Time-limited retention is part of the agreement. Deliveries carry a retention term and we issue destruction certificates when a term ends or a study is withdrawn.
De-identification
DICOM headers are scrubbed to a documented profile, study, series and instance UIDs are remapped through a sealed crosswalk, and studies with burned-in annotation are detected and quarantined rather than shipped.
Provenance
Each batch ships with a hashed manifest, the acceptance verdict for every study and the source-agreement reference, so your counsel can trace the chain of rights.
Need the de-identification methodology and source-agreement summary for a vendor review? Request the compliance pack.
FAQ
CT Abdomen & Pelvis dataset FAQ
Can I get only the portal-venous series?
Yes. We deliver the complete study by default so that your own pipeline can select series, but we can restrict a delivery to the portal-venous series, or to any phase pattern, when the specification asks for it.
Why is lossless compression only 81%?
Part of the source network exported with lossy JPEG at some point in the study history. We record compression history per study and treat a study that was ever lossy as lossy, even if it is lossless now. Specifications that forbid lossy history see roughly 3,500 studies.
How do you confirm the phase of a series?
From DICOM metadata where the series description or contrast timing states it. Where the phase can only be inferred, the study is held for a radiologist read rather than labelled by inference. You choose whether inferred-phase studies are eligible.
Is the abdomen-only subset included?
Around 120 studies cover the abdomen without the pelvis. They are flagged in the profile so your specification can include or exclude them explicitly.
More datasets
Other collections in the catalogue
CTCT Head
Thin-slice, lossless non-contrast CT head.
- 2,100+
- Studies
- 800K+
- DICOM images
- 90%
- With radiologist report
CTCT Chest
Thin-slice CT chest across an older adult population.
- 1,250+
- Studies
- 950K+
- DICOM images
- 83%
- With radiologist report
MRIMRI Spine & MSK
Spine and joint MRI from a routine outpatient population.
- 600+
- Studies
- 115K+
- DICOM images
- 72%
- With radiologist report
Send us your inclusion criteria.
We will return the exact number of studies in this collection that pass, what the rest fail on, and a sample batch your pipeline can load, before any commercial discussion.
Or email [email protected] · Mohali, India